hipaa-compliance
OfficialHIPAA準拠実装、セキュリティ対策、監査ログ、およびデータ保護戦略。
What this skill does
When applied, it prepends a system prompt before your request is sent — no extra calls and no change to how you are billed beyond the added tokens.
--- name: hipaa-compliance description: HIPAA準拠実装、セキュリティ対策、監査ログ、およびデータ保護戦略。 origin: ECC direct-port adaptation version: "1.0.0" --- # HIPAA Compliance Use this as the HIPAA-specific entrypoint when a task is clearly about US healthcare compliance. This skill intentionally stays thin and canonical: - `healthcare-phi-compliance` remains the primary implementation skill for PHI/PII handling, data classification, audit logging, encryption, and leak prevention. - `healthcare-reviewer` remains the specialized reviewer when code, architecture, or product behavior needs a healthcare-aware second pass. - `security-review` still applies for general auth, input-handling, secrets, API, and deployment hardening. ## When to Use - The request explicitly mentions HIPAA, PHI, covered entities, business associates, or BAAs - Building or reviewing US healthcare software that stores, processes, exports, or transmits PHI - Assessing whether logging, analytics, LLM prompts, storage, or support workflows create HIPAA exposure - Designing patient-facing or clinician-facing systems where minimum necessary access and auditability matter ## How It Works Treat HIPAA as an overlay on top of the broader healthcare privacy skill: 1. Start with `healthcare-phi-compliance` for the concrete implementation rules. 2. Apply HIPAA-specific decision gates: - Is this data PHI? - Is this actor a covered entity or business associate? - Does a vendor or model provider require a BAA before touching the data? - Is access limited to the minimum necessary scope? - Are read/write/export events auditable? 3. Escalate to `healthcare-reviewer` if the task affects patient safety, clinical workflows, or regulated production architecture. ## HIPAA-Specific Guardrails - Never place PHI in logs, analytics events, crash reports, prompts, or client-visible error strings. - Never expose PHI in URLs, browser storage, screenshots, or copied example payloads. - Require authenticated access, scoped auth
Use this skill
Add a "skill" field with the skill’s ID to your chat completion request. It is applied server-side before your prompt is sent — no extra calls.
{
"model": "gpt-4o-mini",
"skill": "imp-a7641363-f6ff-4051-92a3-8bf4d88ef3d4",
"messages": [{ "role": "user", "content": "…" }]
}Install the skill, enable it in your dashboard and (optionally) limit it to specific models. It then applies automatically to every matching request — with no "skill" field to send each time.
Set it up in your dashboardMore skills
Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.
Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.
Search and analyze your own session logs (older/parent conversations) using jq.
Create, view, edit, delete, search, move, or export Apple Notes via the memo CLI on macOS.
Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.
Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.
List, add, edit, complete, or delete Apple Reminders and reminder lists via remindctl.
Create, search, and manage Bear notes via grizzly CLI.